Program Leader: Professor Jie Lu
Unique in bringing together the computational intelligence framework with dedicated brain-computer interfaces, this research program focuses on theoretical and methodological study in the field of fuzzy logic, neural networks and other soft computing techniques, targeting applications in big data analytics and optimisation, cognition neuroscience, brain-computer interfaces, machine learning-based intelligence systems, including decision support systems, risk assessment systems, recommendation systems, social media analysis systems, and e-business/e-government systems.
The group enjoys an exceptional track record of ARC including 7 ARC DPs and industry research projects, and has produced more than 300 high-quality research publications. The program currently supervises 10 PhD students, with 15 having graduated previously.
Concept drift detection and reaction for data-driven decision support systems
Unforeseeable changes to patterns that underlie data (concept drift) can lead to reduced accuracy of data-driven prediction, and poor decision outcomes. This study focuses on the development of novel fuzzy competence models to detect and react to changes, integrating them into Decision Support Systems (DSS) for significant enhancement of organisational real-time data analytics and dynamic decision-making.
Fuzzy transfer learning for prediction in data-shortage and rapidly changing environments
This project focuses on the development of a fuzzy transfer learning methodology to provide accurate learning-based prediction, enabling government and industry to better use past experience to inform decision-making and solve problems. Significant benefits will also accrue in the data analytics, business intelligence and decision making research fields.
Recommender systems for personalised government-to-business
This research aims to develop new recommender system model and methodology using computational intelligence, building capacity for e-Government/e-Business systems to offer personalised e-service, transforming government to business service.
Dynamic decision support in warning systems through better management of uncertain information
The influence of uncertain information can render some warning systems ineffective. Applying computerised intelligence techniques, our researchers are developing methodologies and enhancing dynamic decision support software to fuse multi-source uncertain information within a comprehensive platform of warning systems. In addition to improving effectiveness of existing systems, the research will inform the development of new warning systems and related theoretical research.